Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation symbols, especially periods and exclamation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÐIJÑĢÑħÑĸв
    -0.15
    urtles
    -0.14
    «ĺ
    -0.14
    ürlich
    -0.13
    vä
    -0.13
    allet
    -0.13
    -Compatible
    -0.13
    gamber
    -0.13
    oler
    -0.13
     Geile
    -0.13
    POSITIVE LOGITS
    and
    0.23
    which
    0.19
    to
    0.17
    for
    0.17
    of
    0.16
    with
    0.16
    that
    0.16
    as
    0.16
    but
    0.16
    or
    0.15
    Act Density 1.842%

    No Known Activations